Detection of hypernasal speech in children with cleft palate

Akafi, Ehsan; Vali, Mansour; Moradi, Negin

doi:10.1109/icbme.2012.6519688

Cited by 6 publications

(2 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…15 Basic speech spectral characteristics are typically computed using short-time Fourier transform (STFT), while LP-based cepstrum isolates the vocal tract information by removing the glottal excitation source. 20 Mel frequency cepstral coefficients (MFCCs) and one-third octave spectra combine vocal tract information with human auditory characteristics using a logarithmic function. 21 Nasal-formant-based features involve modeling the vocal tract and are crucial cues for hypernasal speech detection.…”

Section: Introductionmentioning

confidence: 99%

Speech Analysis of Patients with Cleft Palate Using Artificial Intelligence Techniques: A Systematic Review

Zhang

Pyon

Chen

et al. 2023

FACE

View full text Add to dashboard Cite

Introduction: This systematic review examines the use of machine learning (ML) algorithms to detect hypernasal speech in patients with cleft palate (CP), which can persist after primary repair surgery, and require revision. Due to a shortage of speech language pathologists (SLPs), automated detection tools could help improve access to care in underserved areas. The study compares the characteristics and accuracy of different types of machine learning algorithms. Methods: On August 18, 2021, searches were conducted across 8 databases: PubMed, SCOPUS, Cochrane, IEEE, ACM, L&LB, PsychInfo, and CINAHL. Search terms used were: (Artificial Intelligence OR Machine Learning OR Neural networks AND Cleft lip OR Cleft palate OR Hypernasality OR Velopharyngeal Insufficiency). To be included, papers needed to describe ML algorithms for CP speech detection and report concordance to human professional speech clinicians. Results: Database searches yielded 135 unique articles. Five articles met full inclusion criteria and 3 additional articles were identified by hand searching references of articles that passed initial screening. These algorithms were categorized as either Feature Dependent non-Deep learning (n = 5) or Feature Dependent deep learning (n = 2) algorithms or Feature Independent deep learning (n = 3) algorithms. Their pooled average concordance were 0.85, 0.93, and 0.91 respectively. Their average training database sizes were 3587, 3921, and 6306 speech samples respectively. Conclusion: Machine learning algorithms have been shown to be an effective tool for the evaluation of hypernasal speech. This systematic review has shown that ML algorithms are able to detect hypernasality with high concordance, consistent with professional speech language clinicians in a rapid, and autonomous manner. ML algorithms can extend the reach of speech language pathologists and complement their gold standard, this long-term outcome monitoring has great potential to improve treatment outcomes.

show abstract

Section: Introductionmentioning

confidence: 99%

Speech Analysis of Patients with Cleft Palate Using Artificial Intelligence Techniques: A Systematic Review

Zhang

Pyon

Chen

et al. 2023

FACE

View full text Add to dashboard Cite

show abstract

“…Ehsan et al put forward an ARMA model with typical number of poles and appropriate number of zeros to model the hypernasal speech signal. And the geometric distance between the cepstral sequences of AR model and ARMA model is used to detect hypernasality [7]. Vijayalakshmi et al find an additional nasal formant in the low-frequency region (around 250Hz).…”

Section: Introductionmentioning

confidence: 99%

The Automatic Detection of Hypernasality in Cleft Palate Speech Based on an Improved Cepstrum Method

Fu¹,

Qian²,

He³

et al. 2017

Proceedings of the 3rd Annual International Conference on Electronics, Electrical Engineering and Information Science (EEEIS 20

View full text Add to dashboard Cite

Abstract. Cleft palate is a birth defect with the resonance between the nasal cavity and oral cavity, which causes an additional nasal formant. And the accurate formant extraction method contributes to hypernasality detection. In this sense, we present a method for formant extraction. The proposed approach uses multi-resolution analysis of automatic segmented filtering combining cepstrum method to accurately extract the formants. It can increase the resolution in the low-frequency region, which is helpful for extracting the addition nasal formant around 250Hz. The proposed technique is tested on 416 vowels /a/ recorded by the West China Hospital of Stomatology, including 216 vowels for normal speech and 210 vowels for cleft palate speech. The formant frequency and formant amplitude are used as acoustic features for hypernasality detection, and the detection accuracy of hypernasality in cleft palate speech is 97.41%.

show abstract